Integrating information from multi-order neighborhoods is a fundamental strategy in Graph Neural Networks (GNNs) for capturing higher-order structural patterns and enhancing the expressive power of node representation...
Integrating information from multi-order neighborhoods is a fundamental strategy in Graph Neural Networks (GNNs) for capturing higher-order structural patterns and enhancing the expressive power of node representations. However, most existing GNNs treat neighbors from different orders as unordered sets and integrate them using static or parallel strategies, thus overlooking the sequential and evolving nature of neighborhood expansion. To address this limitation, we propose a novel GNN framework, SL, which integrates Serialized Neighbor Features with Liquid Neural Networks (LNNs) to enable order-aware, dynamic adaptation of neighbor influence. By modeling neighbor features as ordered sequences and leveraging LNNs' internal feedback dynamics, SL adapts feature extraction in real time based on local context and propagation history. This design offers fine-grained control over hierarchical dependencies and allows dynamic modulation of contributions from different neighborhood layers. SL is model-agnostic and can be seamlessly integrated with both classical and state-of-the-art GNNs. Extensive experiments across ten benchmark datasets show that SL consistently improves node classification accuracy and significantly alleviates over-smoothing in deep GNNs. These results highlight that order-aware and dynamically regulated propagation represents a powerful, flexible alternative to traditional multi-order aggregation, enhancing the adaptability and expressiveness of GNNs for complex graph learning tasks.
Data-driven modeling of nonlinear dynamical systems often require an expert user to take critical decisions a priori to the identification procedure. Recently an automated strategy for data driven modeling of single-i...
详细信息
This paper studies algorithmic strategies to effectively reduce the number of infections in susceptible-infected-recovered (SIR) epidemic models. We consider a Markov chain SIR model and its two instantiations in the ...
详细信息
Considering the sequential clearing of energy and reserves in Europe, enabling inter-area reserve exchange requires optimally allocating inter-area transmission capacities between these two markets. To achieve this, w...
详细信息
The chapter deals with the problem of regulation of linear systems around an equilibrium lying on the boundary of a polyhedral domain where linear constraints on the control and/or the state vectors are satisfied. In ...
详细信息
Continuous-time random disturbances (also called stochastic excitations) due to increasing renewable generation have an increasing impact on power system dynamics;However, except from the Monte Carlo simulation, most ...
详细信息
This paper proposes a network continuous-time susceptible-infected-susceptible (SIS) model coupled with individual opinion dynamics, where the opinion dynamics models an individual’s perceived severity of illness or ...
详细信息
This paper proposes a network continuous-time susceptible-infected-susceptible (SIS) model coupled with individual opinion dynamics, where the opinion dynamics models an individual’s perceived severity of illness or perceived susceptibility. The effects of opinion dynamics on the network SIS model are studied by analyzing the limiting behaviors of the system model, equilibria of the system and their stability.
The study of multiplicative noise models has a long history in control theory but is re-emerging in the context of complex networked systems and systems with learning-based control. We consider linear system identific...
详细信息
The analysis of the photospheric velocity field is essential for understanding plasma turbulence in the solar surface, which may be responsible for driving processes such as magnetic reconnection, flares, wave propaga...
详细信息
learner’s cognitive and metacognitive are key personal profile for individualized teaching. To evaluate learner’s comprehensive characteristics, existing learner model were reviewed. Two challenges of constructing a...
详细信息
learner’s cognitive and metacognitive are key personal profile for individualized teaching. To evaluate learner’s comprehensive characteristics, existing learner model were reviewed. Two challenges of constructing an accurate and comprehensive learner model integrating cognitive and metacognitive were summarized. A plan of constructing a comprehensive learner model was made based on analysis of existing massive online learning environment, sensor information technology and educational data-mining. As a case study, a method of how to map learning data onto learners’ cognitive and metacognitive was proposed based on an analysis of a number of pupils’ Scratch projects. Three mapping table were established. Pupil’s cognitive skill could be evaluated from technology shown from Scratch project, namely, data structure, algorithm, computational practices and overall evaluation. Content shown from Scratch project were used to infer pupil’s cognitive style. Meta-cognitive ability can be measured from computational practices and behavior in programming process.
暂无评论